BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection Paper • 2603.19635 • Published Mar 20 • 12
A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation Paper • 2601.22599 • Published Jan 30 • 6
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention Paper • 2509.23610 • Published Sep 28, 2025 • 15
Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation Paper • 2509.00428 • Published Aug 30, 2025 • 19
Advances in Speech Separation: Techniques, Challenges, and Future Trends Paper • 2508.10830 • Published Aug 14, 2025 • 16
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models Paper • 2505.16211 • Published May 22, 2025 • 18
